Minimal, lightweight JAX implementations of popular models.

Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

BlackJAX is a Bayesian Inference library designed for ease of use, speed and modularity.

Simulating quantum circuits with JAX

Optax is a gradient processing and optimization library for JAX.

Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

[WIP] Vectorized architecture for value-based methods such as DQN and DDPG

A Julia/JuMP Package for Optimal Quantum Circuit Design

An open-source Python framework for hybrid quantum-classical machine learning.